Keras:为大型数据集批量加载图像 [英] Keras: load images batch wise for large dataset

问题描述

由于我有40GB的图像数据集，因此在keras中可能一次仅在内存中加载一批.

Its is possible in keras to load only one batch in memory at a time as I have 40GB dataset of images.

如果数据集很小，我可以使用ImageDataGenerator生成批处理，但是由于数据集很大，我无法将所有图像加载到内存中.

If dataset is small I can used ImageDataGenerator to generator batches but due large dataset I can't load all images in memory.

Keras中是否有任何方法可以执行类似于以下张量流代码的操作:

Is there any method in keras to do something similar to following tensorflow code:

path_queue = tf.train.string_input_producer(input_paths, shuffle= False)
paths, contents = reader.read(path_queue)
inputs = decode(contents)
input_batch = tf.train.batch([inputs], batch_size=2)

我正在使用此方法序列化张量流中的输入，但我不知道如何在Keras中完成此任务.

I am using this method to serialize inputs in tensorflow but I don't know how to achieve this task in Keras.

推荐答案

Keras在其模型中具有方法fit_generator().它接受python generator或keras Sequence作为输入.

Keras has the method fit_generator() in its models. It accepts a python generator or a keras Sequence as input.

您可以像这样创建一个简单的生成器:

You can create a simple generator like this:

fileList = listOfFiles     

def imageLoader(files, batch_size):

    L = len(files)

    #this line is just to make the generator infinite, keras needs that    
    while True:

        batch_start = 0
        batch_end = batch_size

        while batch_start < L:
            limit = min(batch_end, L)
            X = someMethodToLoadImages(files[batch_start:limit])
            Y = someMethodToLoadTargets(files[batch_start:limit])

            yield (X,Y) #a tuple with two numpy arrays with batch_size samples     

            batch_start += batch_size   
            batch_end += batch_size

像这样适合:

model.fit_generator(imageLoader(fileList,batch_size),steps_per_epoch=..., epochs=..., ...)

通常，您将从发生器生成的批次数量传递给steps_per_epoch.

Normally, you pass to steps_per_epoch the number of batches you will take from the generator.

您还可以实现自己的 Keras序列.这需要更多的工作，但是如果您要进行多线程处理，他们建议使用此功能.

You can also implement your own Keras Sequence. It's a little more work, but they recommend using this if you're going to make multi-thread processing.

这篇关于Keras:为大型数据集批量加载图像的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！